Главная

Hugo Larochelle

  1. Training Restricted Boltzmann Machines on Word Observations.

    Втр, 02/28/2012 - 15:01 — SomNambul
    Authors: George E. Dahl, Hugo Larochelle, Ryan P. Adams
    Subjects: Learning
    Abstract

    The restricted Boltzmann machine (RBM) is a flexible tool for modeling
    complex data, however there have been significant computational difficulties in
    using RBMs to model high-dimensional multinomial observations. In natural
    language processing applications, words are naturally modeled by K-ary discrete
    distributions, where K is determined by the vocabulary size and can easily be
    in the hundred thousands.

  2. Conditional Restricted Boltzmann Machines for Structured Output Prediction.

    Пнд, 02/20/2012 - 15:01 — SomNambul
    Authors: Hugo Larochelle, Volodymyr Mnih, Geoffrey E. Hinton
    Subjects: Learning
    Abstract

    Conditional Restricted Boltzmann Machines (CRBMs) are rich probabilistic
    models that have recently been applied to a wide range of problems, including
    collaborative filtering, classification, and modeling motion capture data.
    While much progress has been made in training non-conditional RBMs, these
    algorithms are not applicable to conditional models and there has been almost
    no work on training and generating predictions from conditional RBMs for
    structured output problems. We first argue that standard Contrastive
    Divergence-based learning may not be suitable for training CRBMs.

  3. Learning where to Attend with Deep Architectures for Image Tracking.

    Втр, 09/20/2011 - 15:01 — SomNambul
    Authors: Nando de Freitas, Hugo Larochelle, Misha Denil, Loris Bazzani
    Subjects: Artificial Intelligence
    Abstract

    We discuss an attentional model for simultaneous object tracking and
    recognition that is driven by gaze data. Motivated by theories of perception,
    the model consists of two interacting pathways: identity and control, intended
    to mirror the what and where pathways in neuroscience models. The identity
    pathway models object appearance and performs classification using deep
    (factored)-Restricted Boltzmann Machines. At each point in time the
    observations consist of foveated images, with decaying resolution toward the
    periphery of the gaze.

  4. Loss-sensitive Training of Probabilistic Conditional Random Fields.

    Втр, 07/12/2011 - 15:01 — SomNambul
    Authors: Hugo Larochelle, Richard S. Zemel, Maksims N. Volkovs
    Subjects: Machine Learning
    Abstract

    We consider the problem of training probabilistic conditional random fields
    (CRFs) in the context of a task where performance is measured using a specific
    loss function. While maximum likelihood is the most common approach to training
    CRFs, it ignores the inherent structure of the task's loss function.

  5. Classification of Sets using Restricted Boltzmann Machines.

    Пнд, 03/28/2011 - 15:01 — SomNambul
    Authors: Hugo Larochelle, Jérôme Louradour
    Subjects: Learning
    Abstract

    We consider the problem of classification when inputs correspond to sets of
    vectors. This setting occurs in many problems such as the classification of
    pieces of mail containing several pages, of web sites with several sections or
    of images that have been pre-segmented into smaller regions. We propose
    generalizations of the restricted Boltzmann machine (RBM) that are appropriate
    in this context and explore how to incorporate different assumptions about the
    relationship between the input sets and the target class within the RBM.

  6. Semiparametric Latent Variable Models for Guided Representation.

    Ср, 02/09/2011 - 16:01 — SomNambul
    Authors: Ryan Prescott Adams, Jasper Snoek, Hugo Larochelle
    Subjects: Machine Learning
    Abstract

    Unsupervised discovery of latent representations, in addition to being useful
    for density modeling, visualisation and exploratory data analysis, is also
    increasingly important for learning features relevant to discriminative tasks.
    Autoencoders, in particular, have proven to be an effective way to learn latent
    codes that reflect meaningful variations in data. A continuing challenge,
    however, is guiding an autoencoder toward representations that are useful for
    particular discriminative tasks.

Math-arch

RSS-материал